Tutoring systems become complex and are offering varieties of pedagogical software as course modules, exercises, simulators, systems online or offline, for single user or multi-user. This complexity motivates new forms and approaches to the design and the modelling. Studies and research in this field introduce emergent concepts that allow the tutoring system to interact efficiently with potential users, by enhancing ergonomic service, performing response time and allowing better adaptability. The introduction of concepts such as multi-agent systems (MAS) allowed web technology to improve the process of modeling and designing for distance learning, and thus offer convincing solutions. The presentation of some relevant projects that associate MAS to the Web may highlight the benefits of this association in an innovative way.
The definition of effective pedagogical strategies for coaching and tutoring students according to their needs is one of the most important issues in Adaptive and Intelligent Educational Systems (AIES). The use of a Reinforcement Learning (RL) model allows the system to learn automatically how to teach to each student individually, only based on the acquired experience with other learners with similar characteristics, like a human tutor does. The application of this artificial intelligence technique, RL, avoids to define the teaching strategies by learning action policies that define what, when and how to teach. In this paper we study the performance of the RL model in a DataBase Design (DBD) AIES, where this performance is measured on number of students required to acquire efficient teaching strategies.